<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shamrai-hamolia-2025-deep">
    <titleInfo>
        <title>Deep Language Geometry: Constructing a Metric Space from LLM Weights</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Maksym</namePart>
        <namePart type="family">Shamrai</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Vladyslav</namePart>
        <namePart type="family">Hamolia</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-09</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Galia</namePart>
            <namePart type="family">Angelova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Maria</namePart>
            <namePart type="family">Kunilovskaya</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Marie</namePart>
            <namePart type="family">Escribe</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ruslan</namePart>
            <namePart type="family">Mitkov</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
            <place>
                <placeTerm type="text">Varna, Bulgaria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We introduce a novel framework that utilizes the internal weight activations of modern Large Language Models (LLMs) to construct a metric space of languages. Unlike traditional approaches based on hand-crafted linguistic features, our method automatically derives high-dimensional vector representations by computing weight importance scores via an adapted pruning algorithm. Our approach captures intrinsic language characteristics that reflect linguistic phenomena. We validate our approach across diverse datasets and multilingual LLMs, covering 106 languages. The results align well with established linguistic families while also revealing unexpected inter-language connections that may indicate historical contact or language evolution. The source code, computed language latent vectors, and visualization tool are made publicly available at https://github.com/mshamrai/deep-language-geometry.</abstract>
    <identifier type="citekey">shamrai-hamolia-2025-deep</identifier>
    <location>
        <url>https://aclanthology.org/2025.ranlp-1.130/</url>
    </location>
    <part>
        <date>2025-09</date>
        <extent unit="page">
            <start>1127</start>
            <end>1136</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Deep Language Geometry: Constructing a Metric Space from LLM Weights
%A Shamrai, Maksym
%A Hamolia, Vladyslav
%Y Angelova, Galia
%Y Kunilovskaya, Maria
%Y Escribe, Marie
%Y Mitkov, Ruslan
%S Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era
%D 2025
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F shamrai-hamolia-2025-deep
%X We introduce a novel framework that utilizes the internal weight activations of modern Large Language Models (LLMs) to construct a metric space of languages. Unlike traditional approaches based on hand-crafted linguistic features, our method automatically derives high-dimensional vector representations by computing weight importance scores via an adapted pruning algorithm. Our approach captures intrinsic language characteristics that reflect linguistic phenomena. We validate our approach across diverse datasets and multilingual LLMs, covering 106 languages. The results align well with established linguistic families while also revealing unexpected inter-language connections that may indicate historical contact or language evolution. The source code, computed language latent vectors, and visualization tool are made publicly available at https://github.com/mshamrai/deep-language-geometry.
%U https://aclanthology.org/2025.ranlp-1.130/
%P 1127-1136

Markdown (Informal)

[Deep Language Geometry: Constructing a Metric Space from LLM Weights](https://aclanthology.org/2025.ranlp-1.130/) (Shamrai & Hamolia, RANLP 2025)

• Deep Language Geometry: Constructing a Metric Space from LLM Weights (Shamrai & Hamolia, RANLP 2025)

ACL

• Maksym Shamrai and Vladyslav Hamolia. 2025. Deep Language Geometry: Constructing a Metric Space from LLM Weights. In Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era, pages 1127–1136, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.